SPECOM’2004 Final Program

 

The conference SPECOM’2004 takes place in comfortable three star “Russ” Hotel, located in the heart of the city, in historical, cultural and business center of St. Petersburg (Artilleriyskaya street, 1). The conference halls are located in the following places:

 

Hall 1 - Bank hall, ground floor with own entrance to the right from “Russ” Hotel entrance

Hall 2 - Small conference hall, 4 floor of “Russ” Hotel (to the right from the elevator)

Hall 3 - Small banquet hall, 5 floor of “Russ” Hotel (to the right from the elevator)

Grand Banquet Hall - 5 floor of “Russ” Hotel (to the front from the elevator)

 

Lunches and banquet will take place in the Grand Banquet Hall

Coffee breaks will take place in the Hall 1 and Hall 3

Coffee breaks for Hall 2 will take place in the Hall 3

 

Time

Hall 1

Hall 2

Hall 3

MONDAY, 20 September

8:00-9:00

Registration

-

-

9:00-9:30

Opening Ceremony

9:30-10:30

S1.1 Keynote speeches

10:30-11:00

Coffee Break

11:00-13:00

S1.2 Keynote speeches

13:00-14:00

Lunch

14:00-16:00

S2.1 Multimodal interfaces

S5 Speaker recognition

16:00-16:20

Coffee Break

Coffee Break

16:20-18:00

S2.2 Multimodal interfaces

S9 Speech synthesis

18:00-19:00

-

-

19:00-23:00

Banquet in the Grand Banquet Hall of Hotel “Russ”

TUESDAY, 21 September

9:00-11:00

S3.1 Speech signal processing

S6.1 Speech understanding and natural language processing

INTAS Scientific Workshop

Opening ceremony

S10.1 Strategic Scientific Session

11:00-11:20

Coffee Break

Coffee Break

Coffee Break

11:20-13:00

S3.2 Speech signal processing

S6.2 Speech understanding and natural language processing

S10.2 Strategic Scientific Session

13:00-14:00

Lunch

Lunch

Lunch

14:00-16:00

S3.3 Speech signal processing

S7 Dialogue, ontologies and knowledge representation

S11.1 Presentations of European Research Projects

16:00-16:20

Coffee Break

-

Coffee Break

16:20-18:00

S3.4 Speech signal processing

S11.2 Presentations of European Research Projects

WEDNESDAY, 22 September

9:00-11:00

S4.1 Speech recognition

S8.1 Multimodal services and applications for disabled people

S12.1 Fundamentals of Human-Computer Interaction

11:00-11:20

Coffee Break

Coffee Break

Coffee Break

11:20-13:00

S4.2 Speech recognition

S8.2 Multimodal services and applications for disabled people

S12.2 Fundamentals of Human-Computer Interaction

13:00-14:00

Lunch

Lunch

Lunch

14:00-16:00

S4.3 Speech recognition

-

S12.3 Fundamentals of Human-Computer Interaction

16:00-16:20

Coffee Break

-

16:20-18:00

S4.4 Speech recognition

18:00-18:30

Closing ceremony

 

 

Scientific Program

Session S1. Keynote Speeches

Time: Monday 9:00-13:00, Venue: Hall 1

Chairperson: Rafael Yusupov, SPIIRAS, Russia

 

9:00-9:30          SPECOM'2004 OPENING CEREMONY

9:30-10:00        AUTOMATIC SPEECH RECOGNITION: PAST, PRESENT, AND FUTURE

                         Jean-Paul Haton

                         LORIA/INRIA – Universite Henri Poincare, France

10:00-10:30      PSYCHOGENIC VOICE DISORDERS IN PERFORMERS: A PSYCHODYNAMIC MODEL

                         John S. Rubin

                         Royal National Throat Nose and Ear Hospital, London, UK

10:30-11:00      SEGMENT FEATURES IN DIFFERENT SPEECH STYLES

                         Pavel A. Skrelin

                         Department of Phonetics, St.-Petersburg State University, Russia

11:00-11:30      Coffee Break

11:30-12:00      PHONETIC-ACOUSTICAL PROBLEMS OF PERSONAL VOICE CLONING BY TTS

                         Boris M. Lobanov

                         United Institute of Informatics Problems, Nat. Ac. of Sc. Belarus, Belarus

12:00-12:30      FOREIGN ACCENT PROCESSING IN AUTOMATIC SPEECH RECOGNITION

                         Katarina Bartkova

                         France Telecom, France

12:30-13:00      Models of Speech Perception and Problems of Automatic Speech Recognition

                         Valery I. Galunov

                         St. Petersburg State University, Russia

 

Session S2. Multimodal Interfaces

Time: Monday 14:00-18:00, Venue: Hall 1

Chairperson: Benoit Macq, Universite Catholique de Louvain, Belgium

 

14:00-14:10      MULTIMODAL INTERFACES DAY OPENING

14:10-14:30      3D HUMAN POSTURE ESTIMATION USING GEODESIC DISTANCE MAPS

                         Pedro Correa (1), Ferran Marques (2), Xavier Marichal (1), Benoit Macq (1)

(1) Lab. de Telecom. et Teledetection, Universite Catholique de Louvain (UCL), Belgium

(2) Image Processing Group, Technical University of Catalonia (UPC), Spain

14:30-14:50      COMPARISON OF 2D AND 3D ANALYSIS FOR AUTOMATED CUED SPEECH GESTURE RECOGNITION

                         Alice Caplier, Laurent Bonnaud (1), Sotiris Malassiotis, Michael G. Strintzis (2)

(1) Laboratoire des Images et des Signaux, Grenoble Cedex, France

(2) Research Scientist Informatics & Telematics Institute, Thermi-Thessaloniki, Greece

14:50-15:10      INTEGRATION AND FUSION ASPECTS OF SPEECH AND HANDWRITING MEDIA

                         Sascha Schimke, Thomas Vogel, Claus Vielhauer, Jana Dittmann

Department of Computer Science, ITI Research Group on Multimedia and Security,Magdeburg, Germany

15:10-15:30      FACE MODEL RECONSTRUCTION FOR CZECH AUDIO-VISUAL SPEECH SYNTHESIS

                         Zdenek Krnoul, Milos Zelezny and Petr Cisar

                         University of West Bohemia, Department of Cybernetics, Czech Republic

15:30-15:50      DETECTION OF FACE POSITION AND 3D ORIENTATION IN 2D IMAGE

                         Petr Cisar, Milos Zelezny

                         University of West Bohemia, Department of cybernetics, Czech Republic

15:50-16:10      SPEECH DRIVEN MPEG-4 FACIAL ANIMATION FOR TURKISH

                         Arman Savran, Levent M. Arslan, Lale Akarun

                         Bogazici University Multimedia Laboratory (BUMM), Istanbul, Turkey

16:10-16:30      Coffee Break

16:30-16:50      AN APPROACH TO A MULTIMODAL MAN-MACHINE COMMUNICATION SYSTEM

                         Dario Alonso Rodriguez-Suarez, Maria Jose Sanchez Martinez

Infineon Technologies AG. Corporate Research, Systems Technology. Otto-Hahn-Ring 6, 81739 Munich, Germany

16:50-17:10      SERBIAN EMOTIONAL SPEECH DATABASE: DESIGN, PROCESSING AND EVALUATION

Slobodan T. Jovicic (1), Zorka Kasic (2), Miodrag Dordevic (3), Mirjana Rajkovic (3)

(1) School of Electrical Engineering, Belgrade, Serbia&Montenegro

(2)Faculty of Defectology, Belgrade, Serbia&Montenegro

(3) Institute of Security, Belgrade, Serbia&Montenegro

17:10-17:30      LPFAV2: A NEW MULTI-MODAL DATABASE FOR DEVELOPING SPEECH RECOGNITION SYSTEMS FOR AN ASSISTIVE TECHNOLOGY APPLICATION

                         Vitor Pera, Antonio Moura, Diamantino Freitas

                         Faculty of Engineering, University of Porto, Portugal

17:30-18:00      SIMILAR NOE ROUND TABLE

 

Session S3. Speech Signal Processing

Time: Tuesday 9:00-18:00, Venue: Hall 1

Chairpersons: Andreas Wendemuth, University of Magdeburg, Germany

Yubo GE, Tsinghua University, China

 

9:00-9:20          PERCEPTION OF VOICE-INDIVIDUALITY FOR DISTORTIONS OF ACOUSTIC PARAMETERS

                         Hisao Kuwabara

                         Teikyo Univ. of Science & Technology, Japan

9:20-9:40          NOISY SPEECH RECOGNITION USING STRING KERNELS

                         J. Goddard (1), A. E. Martinez (1), F. M. Martinez (1), H. L. Rufiner (2)

(1) Department of Electrical Engineering, Universidad Autonoma Metropolitana, Iztapalapa, Mexico

(2) Cybernetics Laboratory, Engineering Faculty, National University Entre Rios, Argentina

9:40-10:00        KERNEL METHODS FOR DISCRIMINANT ANALYSIS IN SPEECH RECOGNITION

                         M. Katz, S. Krueger, M. Schaffoener, E. Andelic, A. Wendemuth

                         Dept. of Electrical Engineering, Magdeburg, Germany

10:00-10:20      ITERATIVE IMPLEMENTATION OF THE KERNEL FISHER DISCRIMINANT FOR SPEECH RECOGNITION

                         E. Andelic, M. Katz, S. Kruger, M. Schaffoner, A. Wendemuth

Cognitive Systems Group, Dept. of Electrical Engineering and Information Technology, Otto-Von-Guericke University, Magdeburg, Germany

10:20-10:40      FREE ENERGY CLASSIFICATION AT VARIOUS TEMPERATURES FOR SPEECH RECOGNITION

                         S. Kruger, S. Barth, M. Katz, M. Schaffoner, E. Andelic, A. Wendemuth

                         IESK, Cognitive Systems, University of Magdeburg, Germany

10:40-11:00      INTEGRATION OF ADAPTIVE NOISE CANCELLATION FOR ISOLATED WORD RECOGNITION IN SMART-HOME CONTROL SYSTEMS

                         S.L. Koval, M.B. Stolbov, M.Y. Tatarnikova

                         Speech Technology Center, St. Petersburg, Russia

11:00-11:20      Coffee Break

11:20-11:40      STATE DEPENDENT FEATURE COMPONENT SELECTION FOR NOISE ROBUST ASR

                         Bert Cranen, Johan de Veth

                         Radboud University Nijmegen, The Netherlands

11:40-12:00      SPECTRAL NORMALISATION MFCC DERIVED FEATURES FOR ROBUST SPEECH RECOGNITION

Carlos S. Lima (1), Adriano C. Tavares (1), Carlos A. Silva (1), Jorge F. Oliveira (2)

(1) Department of Industrial Electronics of University of Minho, Portugal

(2) Department of Electrical Engineering, Polytechnic Institute of Leiria, Portugal

12:00-12:20      SUBBAND PAUSE IN SPEECH SIGNAL DETECTION USING MICROPHONE ARRAY IN ROOM WITH REVERBERATION

                         Zoran M. Saric, Slobodan T. Jovicic

                         School of Electrical Engineering, University of Belgrade, Serbia and Montenegro

12:20-12:40      Multiple models for improved speech recognition for non-native speakers

                         Katarina Bartkova, Denis Jouvet

                         France Telecom, France

12:40-13:00      AN EFFICIENT OF NEURAL ADDRESS PREDICTOR APPLIES TO ADDRESS VECTOR QUANTISATION CODEBOOK IN SPEECH PROCESSING

                         J. Srinonchat, S. Danaher, J.I.H. Allen (1), A. Murray (2)

(1) School of Engineering and Technology, Northumbria University, UK

(2) Advanced Technology DivisionTail Electronics, Christchurch, New Zealand

13:00-14:00      Lunch Break

14:00-14:20      NONLINEAR RANDOM FEATURES OF NON-STATIONARY SIGNALS AND APPLICATIONS TO SPEECH RECOGNITION

                         Lingnan Ge, Katsuhiko Shirai (1), Yubo Ge (2)

(1) School of Science and Engineering, Waseda University, Japan

(2) Department of Mathematical Science, Tsinghua University, Beijing, China

14:20-14:40      ADAPTIVE ALGORITHMS FOR PITCH-SYNCHRONOUS SPEECH SIGNAL SEGMENTATION

                         Valery A. Petrushin

                         Accenture Technology Labs, Chicago, USA

14:40-15:00      DATA-DRIVEN FILTER-BANK-BASED FEATURE EXTRACTION FOR SPEECH RECOGNITION

                         Youngjoo Suh, Hoi-Rin Kim

                         School of Engineering, Information and Communications University, Korea

15:00-15:20      ESTIMATING TONGUE-PALATE CONTACT PATTERNS FROM THE SPEECH SIGNAL

                         Asterios Toutios, Konstantinos Margaritis

Parallel and Distributed Processing Laboratory, Department of Applied Informatics University of Macedonia, Greece

15:20-15:40      ANTHROPOMORPHIC FEATURE EXTRACTION ALGORITHM FOR SPEECH RECOGNITION IN ADVERSE ENVIRONMENTS

                         Alexei V. Ivanov, Alexander A. Petrovsky

Computer Engineering Department at the Belarusian State University of Informatics and Radioelectronics, Minsk, Belarus

15:40-16:00      MULTI-ENVIRONMENT MODELS BASED LINEAR NORMALIZATION FOR ROBUST SPEECH RECOGNITION

                         Luis Buera, Eduardo Lleida, Antonio Miguel, and Alfonso Ortega

                         University of Zaragoza, Spain

16:00-16:20      Coffee Break

16:20-16:40      THE INFLUENCE OF AUDIO COMPRESSION ON SPEECH RECOGNITION SYSTEMS

                         Paulo Sirum Ng, Ivandro Sanches

                         Genius Institute of Technology, Manaus, Brazil

16:40-17:00      TOWARDS THE INTEGRATIONS OF STOCHASTIC INFORMATION IN SPEECH TECHNOLOGIES: THE CASE OF SUPRASEGMENTALS

                         Irina Nesterenko

                         St. Petersburg State University, Russia

17:00-17:20      SPEECH SIGNAL ANALYSIS WAVELET-TRANSFORMATION AND SIGNAL PROCESSING AT THE PERIPHERY OF ACOUSTICAL SYSTEM

Vladimir Bondarenko, Vladislav Kotsubinski, Andrew Ponomarev, Dmitriy Velikotski

                         Tomsk State University of the Control System and Radioelectronics, Russia

17:20-17:40      THE INVESTIGATION OF GULLET SPEECH SPECTRUM BY MEANS OF THE RECURSIVE FILTERS SYSTEM

                         Alexander U. Kornilov

                         Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russia

17:40-18:00      IMPLEMENTATION OF TIME-VARYING MODULATION FILTER IN SPEECH ENHANCEMENT SYSTEM

                         A.Shadevsky, A.Petrovsky

Computer Engineering Department at the Belarusian State University of Informatics and Radioelectronics, Belarus

 

Session S4. Speech Recognition

Time: Wednesday 9:00-18:00, Venue: Hall 1

Chairpersons: Chip Wood, Motorola Inc., USA

Dimitri Kanevsky, IBM, USA

 

9:00-9:20          USING DRIVER'S SPEECH TO DETECT COGNITIVE WORKLOAD

                         Chip Wood (1), Kari Torkkola (1), Snehal Kundalkar (2)

(1) Motorola, Center for Human Interaction, Tempe, AZ, USA

(2) Arizona State University, Department of Computer Science, Tempe, AZ, USA

9:20-9:40          SAFETY DRIVER MANAGER

Dimitri Kanevsky, Barbara Churchill, Alex Faisman, David Nahamoo, Roberto Sicconi

                         IBM T. J. Watson Research Center, Yorktown Heights, NY, USA

9:40-10:00        A NOISE ROBUST VOICE INPUT SYSTEM FOR INTERNET SERVICES OVER CELLULAR PHONES

                         Masaki Naito, Kengo Fujita and Tohru Shimizu

                         KDDI R&D Laboratories, Japan

10:00-10:20      IMPROVING ASR PERFORMANCE ON PDA BY CONTAMINATION OF TRAINING DATA

                         Christophe Ris, Laurent Couvreur

                         Multitel & FPMS-TCTS, Mons, Belgium

10:20-10:40      DISTRIBUTED SPEECH RECOGNITION SYSTEM FOR PDA IN WIRELESS NETWORK ENVIRONMENT

                         Soo-Young Suk (1), Ho-Youl Jung (2), Shozo Makino (1), Hyun-Yeol Chung (2)

(1) Graduate School of Eng., Tohoku University, Japan

(2) Department of Information and Communication Eng., Yeungnam University, Korea

10:40-11:00      ADVANCED ACOUSTIC MODELING WITH THE HYBRID HMM/BN FRAMEWORK

                         Konstantin Markov, Satoshi Nakamura

Spoken Language Translation Research Labs, Advanced Telecommunications Research Institute International,Kyoto, Japan

11:00-11:20      Coffee Break

11:20-11:40      A KEYWORD SPOTTING APPROACH BASED ON PSEUDO N-GRAM LANGUAGE MODEL

                         Joo-Gon Kim, Ho-Youl Jung and Hyun-Yeol Chung

                         Department of Information and Communication Eng.,Yeungnam University, Korea

11:40-12:00      ROBUST KEYWORD SPOTTING USING A MULTI-STREAM APPROACH

                         Cheryl Conn, Ji Ming, Philip Hanna

                         School of Computer Science, Queens University Belfast, UK

12:00-12:20      AN APPROACH TO OBTAIN WEIGHTED GRAPHS OF WORDS BASED ON PHONEME DETECTION

                         Jon Ander Gomez, Maria Jose Castro, Emilio Sanchis

Departamento de Sistemas Informaticos y Computacion, Universidad Politecnica de Valencia, Valencia, Spain

12:20-12:40      ON THE USE OF THE NONPARAMETRIC REGRESSION IN NEURAL NETWORK BASED APPROACH APPLIED TO ARABIC SPEECH RECOGNITION

                         Abderrahmane Amrouche (1), Jean Michel Rouvaen (2)

(1) LCPTS, Electronics & Computer Sciences Faculty, USTHB, Algiers, Algeria

(2) IEMN/DOAE Université de Valenciennes, France

12:40-13:00      INCREASING TRAINABILITY OF ASR SYSTEM BY MEANS OF TOP-DOWN CLUSTERING PROCEDURE BASED ON DECISION TREES (VOWEL DATA FOR RUSSIAN)

                         V. Kouznetsov (1), V. Chuchupal (2)

                         (1) Moscow State Linguistic University, Moscow, Russia

                         (2) Computing Center of the Russian Academy of Sciences, Moscow, Russia

13:00-14:00      Lunch Break

14:00-14:20      IMPLEMENTATION OF MORHPEMIC ANALYSIS FOR RUSSIAN SPEECH RECOGNITION

                         A.L. Ronzhin, A.A. Karpov

St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia

14:20-14:40      A GRAPHEME BASED SPEECH RECOGNITION SYSTEM FOR RUSSIAN

                         Sebastian Stuker (1), Tanja Schultz (2)

(1) Institut fur Logik, Komplexitat und DeduktionssystemeUniversitat Karlsruhe (TH), Karlsruhe, Germany

(2) Interactive Systems Laboratories Carnegie Mellon University, Pittsburgh, PA, USA

14:40-15:00      THE FIRST VOICE RECOGNITION APPLICATIONS IN RUSSIAN LANGUAGE FOR USE IN THE INTERACTIVE INFORMATION SYSTEMS

V.A. Zhozhikashvili, M.P. Farkhadov, N.V. Petukhova (1) and A.V. Zhozhikashvili (2)

                         (1) Institute of Control Sciences RAS, Moscow, Russia

                         (2) Institute for Information Transmission Problems RAS, Moscow, Russia

15:00-15:20      AUTOMATIC VOWEL RECOGNITION IN FLUENT SPEECH (ON THE MATERIAL OF THE RUSSIAN LANGUAGE)

                         Daniil A. Kocharov

                         Saint-Petersburg State University, Russia

15:20-15:40      TURKISH RADIOLOGY DICTATION SYSTEM

                         Ebru Arisoy, Levent M. Arslan

Bogazici University, Electrical and Electronic Engineering Department, Istanbul, Turkey

15:40-16:00      AN ACOUSTIC ANALYSIS OF MODERN PERSIAN VOWELS

                         Ali Akbar Ansarin

                         Tabriz University, Iran

16:00-16:20      Coffee Break

16:20-16:40      AUTOMATIC PUNCTUATION ANNOTATION IN CZECH BROADCAST NEWS SPEECH

                         Jachym Kolar, Jan Svec, Josef Psutka

                         University of West Bohemia in Pilsen, Department of Cybernetics, Czech Republic

16:40-17:00      TOWARDS ACOUSTIC MODELING OF LITHUANIAN SPEECH

                         Darius Silingas (1), Sigita Laurinciukaite, Laimutis Telksnys (2)

                         (1) Vytautas Magnus University, Kaunas, Lithuania

                         (2) Institute of Mathematics and Informatics, Vilnius, Lithuania

17:00-17:20      CONTROL OF A MOBILE ROBOT USING SPOKEN COMMANDS

Jesus Savage, Emmanuel Hernandez, Gabriel Vazquez, Adalberto Hernandez (1), Andrey Ronzhin (2)

(1) Laboratory of Biorobotics, University of Mexico, UNAM, Mexico

(2) St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia

17:20-17:40      THAI CONNECTED DIGIT SPEECH RECOGNITION USING HIDDEN MARKOV MODELS

Amarin Deemagarn, Asanee Kawtrakul

Kasetsart University, Bangkok, Thailand

 

Session S5. Speaker Recognition

Time: Monday 14:00-16:20, Venue: Hall 3

Chairperson: Juhani Saastamoinen, University of Joensuu, Finland

 

14:00-14:20      AUTOMATIC SPEAKER RECOGNITION FOR SERIES 60 MOBILE DEVICES

                         Juhani Saastamoinen, Evgeny Karpov, Ville Hautamaki, Pasi Franti

                         University of Joensuu, Dept. of Computer Science, Finland

14:20-14:40      FUSION OF SPECTRAL FEATURE SETS FOR ACCURATE SPEAKER IDENTIFICATION

                         Tomi Kinnunen, Ville Hautamaki, and Pasi Franti

                         Department of Computer Science University of Joensuu, Finland

14:40-15:00      SYMMETRIC DISTORTION MEASURE FOR SPEAKER RECOGNITION

                         Evgeny Karpov, Tomi Kinnunen, Pasi Franti

                         Department of Computer Science University of Joensuu, Finland

15:00-15:20      DOUBLE CLUSTERING ALGORITHM APPLIED TO SPEAKER DEPENDENT INFORMATION

                         J. Srinonchat, S. Danaher, J.I.H. Allen (1), A. Murray (2)

(1) School of Engineering and Technology, Northumbria University, UK

(2) Advanced Technology DivisionTail Electronics, Christchurch, New Zealand

15:20-15:40      THE DISCRIMINANT-STOCHASTIC APPROACH OF THE SPEAKER VERIFICATION FOR ENTRY CONTROL BY THE BIOMETRICAL TECHNOLOGIES

                         A.S. Rylov, V.A.Chyzhdzenka (1), T.V. Leukouskaya (2)

(1) Institute of problems of criminology, criminalistic sand forensic eskpertise the Department of Justice republic of Belarus

(2) National Academy of Science of Belarus United Institute of informatics Problems

15:40-16:00      AUTOMATIC ESTIMATION OF HUMAN’S PSYCHOPHYSIOLOGICAL STATE BY SPEECH

                         A.L. Ronzhin, I.V. Lee, A.A. Karpov (1), V.A. Skormin (2)

                         (1) St. Petersburg Institute for Informatics and Automation, Russia

                         (2) Binghamton University, Binghamton, NY, USA

16:00-16:20      Coffee Break

 

Session S9. Speech Synthesis

Time: Monday 16:20-18:00, Venue: Hall 3

Chairperson: Boris Lobanov, United Institute of Informatics Problems NASB, Belarus

 

16:20-16:40      POLISH TTS IN MULTI-VOICE SLAVONIC LANGUAGES SPEECH SYNTHESIS SYSTEM

Edward Shpilewski, Bozhena Piurkowska, Janush Rafalko(1),Boris Lobanov, Vitaly Kiselov, Liliya Tsirulnik(2)

(1) Institute of Computer Sciences, University of Bialystok, Poland

(2) United Institute of Information Problems, Nat. Ac. of Sc. of Belarus, Belarus

16:40-17:00      THE DETERMINATION OF VOWEL PERCEPTION LIMITS USING SPEECH SYNTHESIS

                         Les Doherty

                         Spectral Dynamics Pty Ltd, Australia

17:00-17:20      D-SCRIPT MODEL FOR SYNTHESIS AND ANALYSIS OF EMOTIONAL SPEECH

                         Artemy A. Kotov

                         Russian State Univerisity for the Humanities, Institute of Linguistics, Russia

17:20-17:40      UNIT SELECTION SPEECH SYNTHESIS USING PHONETIC-PROSODIC DESCRIPTION OF SPEECH DATABASES

                         Tetyana Lyudovyk, Mykola Sazhok

International Research/Training Center for Information Technologies and Systems, Kyiv, Ukraine

17:40-18:00      THE TENDENCIES AND FEATURES OF AN EXCITATION SIGNAL MODELING IN DIGITAL DEVICES OF THE SPEECH ANALYSIS AND SYNTHESIS

                         Alexander Rybolovlev, Sergej Zabirnik (1), Michail Galkin (2)

                         (1) Academy of Special communication of Russia, Oryol, Russia

                         (2) Group of government communication, Syzran, Russia

 

Session S6. Speech Understanding and Natural Language Processing

Time: Tuesday 9:00-13:00, Venue: Hall 2

Chairperson: Valery Galunov, St. Petersburg State University, Russia

 

9:00-9:20          FROM ARTIFICIAL INTELLIGENCE TO SMART ENVIRONMENT: ON THE PROBLEM OF SPEECH RECOGNITION

                         V.I. Galunov (1), N.G. Kouznetsov (2), A.N. Soloviev (1)

                         (1) St. Petersburg State University, Russia

                         (2) NLK Software Consulting, Waterloo, Canada

9:20-9:40          STATISTICAL MACHINE TRANSLATION OF SERBIAN-ENGLISH

                         Maja Popovic (1), Slobodan Jovicic, Zoran Saric (2)

(1) Lehrstuhl fur Informatik VI - Computer Science Department, RWTH Aachen University, Germany

(2) School of Electrical Engineering, Beograd, Serbia and Montenegro

9:40-10:00        MEMORY-BASED ROBUST INTERPRETATION OF RECOGNISED SPEECH

                         Piroska Lendvai, Antal van den Bosch (1), Emiel Krahmer(2), Sander Canisius (1)

(1) ILK / Dept. Computational Linguistics and AI

(2) Dept. Communication and CognitionFaculty of Arts, Tilburg University, The Netherlands

10:00-10:20      NLP AND ATTRIBUTION OF PSEUDONYMIC TEXTS:WHO IS REALLY THE AUTHOR OF THE "QUIET FLOWS THE DON"

                         Michail A. Marusenko (1), Rajmund H. Piotrowski (2), Yuri V. Romanov (2)

                         (1) Saint Petersburg State University, Russia

                         (2) Herzen State Pedagogical University of Russia, Russia

10:20-10:40      THE CALCULATION OF THE POSITIONAL RELATIONSHIP OF ELEMENTS IN DATA ARRAYS (FORMAL ANALYSIS OF THE STRUCTURED DATA COMPOSITION)

                         Alexander S. Gumenjuk

                         Omsk State Technical University, Omsk, Russia

10:40-11:00      TURN-TAKING IN SOCIAL TALK DIALOGUES: TEMPORAL, FORMAL ANDFUNCTIONAL ASPECTS

                         Louis ten Bosch, Nelleke Oostdijk (1), Jan Peter de Ruiter (2)

                         (1) Radboud University Nijmegen, The Netherlands

                         (2) Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands

11:00-11:20      Coffee Break

11:20-11:40      FUZZY GRANULES AS A BASIC WORD REPRESENTATION FOR COMPUTING WITH WORDS

                         Santiago Aja-Fernandez, Carlos Alberola-Lopez

                         ETS Ingenieros de TelecomunicacionUniversidad de Valladolid, Spain

11:40-12:00      REPRESENTATION OF FORMAL LOGICAL KNOWLEDGE BY THE MEANS OF NATURAL LANGUAGE

                         Elena G. Ivanova

                         Taganrog State University of Radioengineering, Taganrog, Russia

12:00-12:20      SEMANTIC-PRAGMATIC PROCESSING OF NATURAL LANGUAGE FOR AUTOMATIC SPEECH UNDERSTANDING SYSTEMS

                         I.V. Lee, A.L. Ronzhin, A.A. Karpov

St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia

12:20-12:40      SPOKEN DISCOURSE AND PERCEPTUAL RULES OF ITS SEMANTIC RECONSTRUCTION

                         Potapova R.K., Khitina M.V., Yakovleva E.B.

                         Department of Applied Linguistics, Moscow State Linguistic University, Russia

12:40-13:00      SYSTEMS ANALYSIS: A SEMIOTIC APPROACH TO PROBLEM AND PURPOSE REPRESENTATION

                         Ljudmila M. Lukianova

                         St. Petersburg Institute for Informatics and Automation, St. Petersburg, Russia

13:00-14:00      Lunch Break

 

Session S7. Dialogue, Ontologies and Knowledge Representation

Time: Tuesday 14:00-16:00, Venue: Hall 2

Chairperson: Irina Kobozeva, Moscow State Lomonosov University, Russia

 

14:00-14:20      TYPES OF INFORMATION FOR THE MULTIMEDIA DICTIONARY OF RUSSIAN DISCOURSE MARKERS

                         I.M. Kobozeva, L.M. Zakharov

Moscow State Lomonosov University, Russia

14:20-14:40      ONTOLOGY OF THE SUBJECT DOMAIN “SPEECH SIGNALS RECOGNITION AND SYNTHESIS”

                         Valery I. Galunov (1), Boris M. Lobanov (2), Nicolay G. Zagoruiko (3)

(1) St. Petersburg State University, Russia

(2) United Institute of Informatics Problems NASB, Minsk, Belarus; (3) Institute of Mathematics SD RAS, Novosibirsk, Russia

14:40-15:00      PARAMETER SETTING OF CONNECTIONIST CLASSIFIERS IN A DIALOGUE SYSTEM

                         Wladimiro Diaz (1), Maria Jose Castro (2), Francesc J. Ferri (1)

(1) Dep. d’Informatica, Universitat de Valencia, Spain

(2) Dep. Sistemes Informatics i Computacio, Universitat Politecnica de Valencia, Spain

15:00-15:20      DIALOGUE ACT CLASSIFICATION USING A BAYESIAN APPROACH

                         Sergio Grau (1), Emilio Sanchis (1), Maria Jose Castro (1), and David Vilar (2)

(1) Departament de Sistemes Informatics i Computacio, Universitat Politecnica de Valencia, Spain

(2) Lehrstuhl fur Informatik VIComputer Science DepartmentRWTH Aachen University, Germany

15:20-15:40      MODELING OF DIALOGUE REASONING AND ITS APPLICATIONS

                         Ekaterina P. Sosnina

                         Ulyanovsk State Technical University, Ulyanovsk, Russia

 

Session S8. Multimodal Services and Applications for Disabled People

Time: Wednesday 9:00-13:00, Venue: Hall 2

Chairperson: Dimitrios Tzovaras, Informatics and Telematics Institute, Greece

 

9:00-9:20          CYBERGRASP AND PHANTOM INTEGRATION: ENHANCED HAPTIC ACCESS FOR VISUALLY IMPAIRED USERS

Georgios Nikolakis, Dimitrios Tzovaras (1), Serafim Moustakidis (2), Michael G. Strintzis (1,2)

(1) Informatics and Telematics Institute, Centre for Research and Technology Hellas, Greece

(2) Electrical and Computer Engineering Department,Aristotle University of Thessaloniki, Greece

9:20-9:40          HAPTIC BROWSER: A HAPTIC ENVIRONMENT TO ACCESS HTML PAGES

                         G. Nikolakis, I. Tsampoulatidis, D. Tzovaras (1) and Michael G. Strintzis (1,2)

(1) Informatics and Telematics Institute, Centre for Research and Technology Hellas, Greece

(2) Electrical and Computer Engineering Department,Aristotle University of Thessaloniki, Greece

9:40-10:00        ASSISTIVE MULTIMODAL SYSTEM BASED ON SPEECH RECOGNITION AND HEAD TRACKING

Alexey A. Karpov, Andrey L. Ronzhin (1), Alexander I. Nechaev, Svetlana E. Chernakova (2)

(1) Speech Informatics Group

(2) Robotics Laboratory

St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia

10:00-10:20      PRONUNCIATION SCORING FOR THE HEARING-IMPAIRED

                         Oytun Turk, Levent M.Arslan

                         BUMM, Electrical & Electronics Eng. Dept., Bogazici University, Istanbul, Turkey

10:20-10:40      SYPOLE: MOBILE READING ASSISTANT FOR BLIND PEOPLE

                         Vincent Gaudissart, Silvio Ferreira, Celine Thillou, Bernard Gosselin

                         Faculte Polytechnique de Mons, Mons, Belgium

10:40-11:00      A PERFORMANCE STUDY OF A RECOGNITION SYSTEM FOR GREEK SIGN LANGUAGE ALPHABET LETTERS

                         Vassilia N. Pashaloudi, Konstantinos G. Margaritis

Parallel and Distributed Processing Laboratory, Department of Applied Informatics, University Of Macedonia, Thessaloniki, Greece

11:00-11:20      Coffee Break

11:20-11:40      A SYSTEM FOR THE PROCESSING OF INFANT CRY TO RECOGNIZE PATHOLOGIES IN RECENTLY BORN BABIES WITH NEURAL NETWORKS

                         Orion F. Reyes-Galaviz(1), Carlos Alberto Reyes-Garcia(2)

                         (1) Instituto Tecnologico de Apizaco, Mexico

                         (2) Instituto Nacional de Astrofisica Optica y Electronica, Mexico

11:40-12:00      NEW APPROACH TO SUPPORTING COMMUNICATION FOR BLINDS: APPLIED LEARNING SYSTEM

                         George V. Losik, Sergey V. Kirpich and Oleg G. Sizonov

National Academy of Sciences of Belarus United Institute of Informatics Problems, Minsk, Belarus

12:00-12:20      THE BIOFEEDBACK PROGRAM FOR SPEECH REHABILITATION OF ONCOLOGICAL PATIENTS AFTER FULL LARYNX REMOVAL SURGICAL TREATMENT

                         Alexander U. Kornilov

                         Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russia

12:20-13:00      ROUND TABLE

 

 

INTAS Strategic Scientific Workshop
“Development of perspective applications of Human-Computer Interaction for Information Society”

 

Session S10. INTAS Workshop: Strategic Scientific Session

Time: Tuesday 9:00-13:00, Venue: Hall 3

Chairperson: Patrizia Asirelli, Scientific Officer, INTAS

 

9:00-9:10          INTAS OPENING CEREMONY

9:10-9:40          INTAS: YOUR PARTNER FOR PRESENT AND FUTURE NIS COOPERATION IN INFORMATION TECHNOLOGY

                         Patrizia Asirelli

                         INTAS, Belgium

9:40-10:10        SURVEY OF PARTICIPATION OF RUSSIA IN FP6

                         Alexey Ivanov

                         Saint Petersburg Electrotechnical University, Russia

10:10-10:40      Russian national innovation system

                         Eugeny Smirnov

The Advisory Panel for problems of the innovation policy and development of human potential, Council of Federation, Federal Assembly of the Russian Federation

10:40-11:10      INTAS and Scientific Society of St. Petersburg - the Experience of Cooperation

Nelly Didenko, Andrey Petrovsky

St. Petersburg Scientific Centre of the Russian Academy of Sciences, Euroscience Local Section in Russia

11:10-11:30      Coffee Break

11:30-12:00      RFBR grants and Financial Support of Basic Research in St. Petersburg

Andrey Petrovsky (1), Nelly Didenko (2)

(1) Regional Representative of the Russian Foundation for Basic Research in North-West Russia (St. Petersburg)

(2) St. Petersburg Scientific Centre of the Russian Academy of Sciences

12:00-12:20      The long-term strategy of the "Russian Speech Technologies" Consortium is to develop the national bespoke program "Russian speech" and its place in the global IT world

                         S.V Avdeev, A.S. Narin'yni, E.G. Kneller

"Russian Speech Technologies" Consortium, Russia

12:20-12:40      DEVELOPMENT OF PARTNERSHIP NETWORKS IN THE NORTH-WEST EUROPE IN THE FRAMEWORK OF INTERNATIONAL COOPERATION IN ICT SPHERE

                         Irina V. Arefieva (1), Alexander S. Bikkulov (2), Andrey V. Chugunov (3)

(1) St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia

(2) St. Petersburg State University, Russia; (3) PRIOR North-West, St. Petersburg, Russia

12:40-13:00      PRESENTATION OF THE SIMILAR NETWORK OF EXCELLENCE

                         Benoit Macq, Benoit Michel

                         SIMILAR NoE, Universite Catholique de Louvain, Belgium

 

Session S11. INTAS Workshop: Presentations of European Research Projects

Time: Tuesday 14:00-18:00, Venue: Hall 3

Chairperson: Taras Vintsiuk, IRTC, Ukraine

 

14:00-14:30      UKRAINIAN ACTIVITY IN SPEECH AND LANGUAGE INFORMATION TECHNOLOGY RELATING TO INTAS CO-OPERATION

                         Taras K. Vintsiuk

International Research-Training Centre for Information Technologies and Systems – IRTC, Kyiv, Ukraine

14:30-15:00      TO INTERACT MEANS TO UNDERSTAND EACH OTHER

                         Alexander S. Narin'yani

                         Russian Research Institute for Artificial Intelligence, Moscow, Russia

15:00-15:30      INTELLECTUAL ROBOTS IN RUSSIA: EXPERIENCE OF DEVELOPMENT AND ROBOCUP PARTICIPATION

                         Lev A. Stankevich

                         St. Petersburg State Polytechnic University, Russia

15:30-15:50      CREATION OF RUSSIAN SPEECH DATABASES: DESIGN, PROCESSING, DEVELOPMENT TOOLS

Vladimir L. Arlazarov (1), Dimitri S. Bogdanov (1), Olga F. Krivnova (2), Aleksandr Ya. Podrabinovitch (1)

                         (1) Institute for System Analysis of Russian Academy of Science, Moscow, Russia

                         (2) M.V. Lomonosov Moscow State University, Faculty of philology, Russia

15:50-16:00      Future Work at Samsung Electronics

                         Hong Sik Ju, Alexei Latyshev

                         Samsung Research Center, Moscow, Russia

16:00-16:20      Coffee Break

16:20-16:40      DELIVERING VIDEO-BASED IST SERVICES INTO EUROPEAN HOMES - NETWORKED HOME PROJECT IN THE IST PROGRAMME

                         Oleg V. Makhrovskiy, Vitaly S. Shibanov

                         Research Institute Rubin, St. Petersburg, Russia

16:40-17:00      HOLOGRAPHIC TECHNIQUE FOR LINGUISTIC MODELLING

                         Alexander V.Pavlov

                         S.I. Vavilov State Optical Institute, St. Petersburg, Russia

17:00-17:20      THE EVENT CALCULUS IMPLEMENTATION USING ILOG JRULES FOR SECURITY POLICY VERIFICATION

                         Igor V. Kotenko, Artem V. Tishkov, Maria Tishkova

                         St. Petersburg Institute for Informatics and Automation, Russia

17:20-18:00      INTAS ROUND TABLE

 

Session S12. INTAS Workshop: Fundamentals of Human-Computer Interaction

Time: Wednesday 9:00-16:30, Venue: Hall 3

Chairperson: Boris Sokolov, SPIIRAS, Russia

 

9:00-9:20          MODELS AND METHODS FOR FLEXIBLE REASSIGNMENT OF CONTROL FUNCTIONS IN MAN-MACHINE SYSTEMS

                         Boris V. Sokolov

                         St. Petersburg Institute for Informatics and Automation, Russia

9:20-9:40          INTELLECTUALIZATION FOR MAN-MACHINE INTERFACE AND NETWORK CONTROL IN MULTI-AGENT INFOTELECOMMUNICATION SYSTEMS OF NEW GENERATION

                         Adil V. Timofeev

                         Saint-Petersburg Institute for Informatics and Automation of RAS

9:40-10:00        A NEW APPROACH TO THE PROBLEM OF WORD SEGMENTATION

                         W.A. Antciperov, W.A. Morozov, S.A. Nikitov

                         Institute of Radioengineering and Electronics RAS, Moscow, Russia

10:00-10:20      FEEDBACK DESIGN PHILOSOPHY IN THE COMPUTER ASSISTED LANGUAGE LEARNING SYSTEMS

                         M.A. Degtyarev, S.N. Krinov, Yu.N. Marchuk

                         Moscow State Regional University, Russia

10:20-10:40      DESIGN AND IMPLEMENTATION OF MULTI-AGENT MAN-MACHINE INTERFACE ON THE BASE OF VIRTUAL REALITY MODELS

                         A.V. Timofeev, V. Andreev, I.E. Gulenko, O.A. Derin (1), M.V. Litvinov (2)

(1) Saint-Petersburg Institute for Informatics and Automation of RAS

(2) Baltic State Technical University “Voenmech”, St. Petersburg, Russia

10:40-11:00      SIGNS AND SPEECH: TWO FORMS OF HUMAN COMMUNICATION

                         Alexander Voskressenski

Boarding school No. 101 for deaf children, Moscow, Russia

11:00-11:20      Coffee Break

11:20-11:40      SOME SYNERGETIC MECHANISMS OF SYSTEM OF SPEECH

                         Natalia Yu. Zaytseva

                         Herzen State Pedagogical University of Russia, St. Petersburg, Russia

11:40-12:00      ONTOSMINER FAMILY: MULTILINGUAL IE SYSTEMS

                         Irina V. Efimenko, Vladimir F. Khoroshevsky, Victor P. Klintsov

                         AviComp AG, Moscow, Russia

12:00-12:20      THE METRICS FOR QUANTITATIVE EVALUATION OF USER INTERFACE USABILITY CONSTRUCTION METHODOLOGY

                         Olga A. Belaya

                         SmartPhoneLabs LLC, St.Petersburg, Russia

12:20-12:40      ON THE TEMPORAL COMPONENT OF INTONATIONAL PHRASING

                         N. Volskaya, S. Stepanova

                         St. Petersburg State University, Russia

12:40-13:00      Development of multi-voice and multi-language Text-to-Speech (TTS) and Speech-to-Text (STT) conversion system (languages: Belorussian, Polish, Russian)

Ruediger Hoffmann (1), Edward Shpilewsky (2), Boris Lobanov (3), Andrey Ronzhin (4)

                         (1) Technische Universität Dresden, Germany

                         (2) University Bialystok, Poland

                         (3) United Institute of Information Problems of the National Academy of Sciences of Belarus, Belarus

                         (4) St. Petersburg Institute for Informatics and Automation, Russia

13:00-14:00      Lunch Break

14:00-14:20      Relative Study of  Speaker Recognition Models

V.V. Geppener, A.S. Haider

St.-Petersburg State Electrotechnical University, Department of Computer Software and Applications

14:20-14:40      FREE TEXT USER REQUEST PROCESSING IN THE SYSTEM “KSNET”

Alexander V. Smirnov, Mikhail P. Pashkin, Nikolai G. Chilov, Tatiana V. Levashova, and Andrew A. Krizhanovsky

                         St. Petersburg Institute for Informatics and Automation, Russia

14:40-15:00      Information System “Nationalities of Russia Ethnography”: Problems of Textual, Visual and Audio Data Integration

Igor I. Vernjaev (1), Olga M. Fishman (2), Andrey V. Chugunov (3), Natalja I. Ivanovskaja(2), Vladimir B. Pankratov, Pavel P. Tsherbakov (1)

(1) St. Petersburg State University, Russia

                         (2) Russian Museum of Ethnography, St. Petersburg, Russia

                         (3) St. Petersburg State University, Interdisciplinary Center, Russia

15:00-15:20      LANGUAGE AND MECHANISM OF SPEECH AS CONTROLLING INTERFACE WITH ENVIRONMENT

                         Ivan H. Vardanyan

                         NGO “Computers for Saving the Earth”, Yerevan-19, Armenia

15:20-15:40      USING OF SUSTEMS OF ARTIFICIAL SPEECH IN TRAINING THE STUDENTS OF THE PHILOLOGICAL DEPARTMENT

                         L. Titova, A. Mirgalina

                         Bashkir State Pedagogical University, Russia

15:40-16:10      INTAS ROUND TABLE

 

 


SPECOM'2004 Homepage